Power marketing data management method and system

Abstract

The invention discloses a power marketing data management method and system, and relates to the technical field of power marketing data management, and the method comprises the steps: collecting the power consumption data of a user in real time, and carrying out the preprocessing of the collected data through an edge computing device; on the edge computing device, analyzing the preprocessed data, identifying an abnormal power consumption mode, and screening normal user power consumption data according to an identification result; sending the normal power utilization data of the user to a central server for storage, and analyzing the power utilization habit of the user by the central server according to the normal power utilization data of the user; a personalized energy-saving suggestion algorithm is developed according to the power utilization habit of the user, and targeted energy-saving suggestions are recommended to the user; and collecting user feedback, and optimizing the personalized energy-saving suggestion algorithm according to the user feedback. Through real-time data collection and preprocessing, anomaly detection, secure data transmission and user power utilization habit analysis, a personalized energy-saving suggestion algorithm is developed, user experience is optimized, energy conservation and emission reduction are promoted, and data security is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power marketing data management, and in particular to a power marketing data management method and system. Background Art

[0002] With the rapid development of the power industry and the advancement of information technology, power marketing has gradually introduced advanced technologies such as big data, cloud computing, and the Internet of Things to achieve refined management and services. Traditional data management methods mainly rely on manual processing, which is inefficient and error-prone. In recent years, with the application of technologies such as edge computing and machine learning, the speed and accuracy of data processing have been significantly improved. Edge computing devices can realize real-time data processing and reduce the pressure on central servers; while machine learning algorithms can help identify abnormal data, tap potential value, and provide users with more accurate services. In addition, the maturity of encryption technology and data integrity verification methods also provides guarantees for the secure transmission of data.

[0003] Although the above technologies have played an important role in power marketing data management, there are still some shortcomings. First, the real-time processing capabilities of large amounts of complex data are limited, especially when dealing with large-scale data sets, traditional data processing methods may cause delays and errors. Second, the accuracy of anomaly detection algorithms needs to be improved, because incorrect anomaly detection may cause normal power consumption patterns to be misjudged as abnormal, affecting user experience. Third, the generation of personalized energy-saving suggestions is often based on simple statistical analysis, lacking sufficient intelligence and personalization, and it is difficult to meet the specific needs of different users. Finally, the user feedback mechanism is not sound enough, and it is difficult to obtain effective user feedback in a timely manner to improve services. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a power marketing data management method and system to solve the problems in the prior art of insufficient real-time big data processing capability, low anomaly detection accuracy, lack of intelligence in personalized energy-saving suggestions, and imperfect user feedback mechanism.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for managing power marketing data, which includes collecting users' power consumption data in real time, and preprocessing the collected data using an edge computing device; analyzing the preprocessed data on the edge computing device to identify abnormal power consumption patterns, and screening normal user power consumption data based on the identification results; sending the user's normal power consumption data to a central server for storage, and the central server analyzing the user's power consumption habits based on the user's normal power consumption data; developing a personalized energy-saving suggestion algorithm based on the user's power consumption habits, and recommending targeted energy-saving suggestions to the user; collecting user feedback, and optimizing the personalized energy-saving suggestion algorithm based on the user feedback.

[0008] As a preferred solution of the power marketing data management method of the present invention, the real-time collection of user power consumption data and the use of edge computing equipment to pre-process the collected data are as follows:

[0009] Install smart meters at the metering points of electricity users to collect users' electricity consumption data in real time, including the amount of electricity used, the time of use, and the frequency of use. At the same time, the collected user electricity consumption data is sent to the edge computing device.

[0010] Edge computing devices are deployed near smart meters to process missing values, standardize, and process outliers for the collected user electricity consumption data.

[0011] As a preferred solution of the power marketing data management method of the present invention, the pre-processed data is analyzed in real time on the edge computing device to identify abnormal power consumption patterns, and the user power consumption data marked as normal is screened according to the identification results. The specific steps are as follows:

[0012] An isolation forest model is constructed based on the preprocessed user electricity consumption data;

[0013] Set the number of trees in the isolation forest and the number of samples used for each tree according to actual needs;

[0014] Using the average path length and sample size, the abnormal score of user electricity consumption data is calculated. The expression is:

[0015]

[0016] Among them, S(X,n) represents the anomaly score of data point X, n is the number of samples used in each tree, E[h(X)] is the average path length to reach the leaf node, h(X) is the number of edges required for the data point to reach the leaf node from the root node of the tree, X is the preprocessed user electricity consumption data, and c9n) represents the average path length of a complete binary tree with n nodes;

[0017] Based on the distribution of historical data, define an abnormal deviation threshold A to identify abnormal data points;

[0018] When S(X,n)>A, mark the current data point as abnormal power consumption data;

[0019] When S(X,n)≤A, mark the current data point as normal power consumption data;

[0020] The data points marked as normal are filtered out to form a user's normal electricity consumption data set.

[0021] As a preferred solution of the power marketing data management method of the present invention, wherein: the normal power consumption data of the user is sent to the central server for storage, the specific steps are as follows:

[0022] Pack the filtered normal power consumption data into a data packet P;

[0023] The data packet P is encrypted using the AES-256 encryption algorithm, and the encrypted data packet is sent from the edge computing device to the central server via a secure TCP / IP protocol;

[0024] The central server receives the data packet P from the edge computing device, decrypts the data in the received data packet P and verifies the data integrity, and stores the decrypted data in the database of the central server.

[0025] As a preferred solution of the power marketing data management method of the present invention, the central server analyzes the user's power usage habits based on the user's normal power usage data. The specific steps are as follows:

[0026] Using the K-means algorithm, calculate the cluster center c closest to the normal data point X' i , cluster the data points in the data packet P, the expression is:

[0027]

[0028] Among them, C(X') represents the index number of the cluster to which the normal data point X' belongs, X' is the normal data point that has been screened out, and the data point X' and the cluster center c are calculated. i The distance between

[0029] The average power consumption of the cluster to which the data point belongs is calculated by the cluster index number C(X') to which the data point belongs. The expression is:

[0030]

[0031] Among them, X' i represents the i-th data point marked as normal, Represents data point X' i Power consumption, C(X') j represents the set of all data points contained in the jth cluster, |C(X') j | represents the total number of data points in the jth cluster, M j represents the average power consumption of the jth cluster;

[0032] By calculating the average power consumption M of all clusters j Sort by size and select the median as the electricity consumption standard u;

[0033] When M j >u, it means that the current clustered user group has a high daily electricity consumption;

[0034] When M j When ≤u, it means that the daily electricity consumption of the current clustered user group is low.

[0035] As a preferred solution of the power marketing data management method of the present invention, wherein: the personalized energy-saving suggestion algorithm is developed according to the user's power consumption habits to recommend targeted energy-saving suggestions to the user. The specific steps are as follows:

[0036] By statistical analysis, each data point X' is extracted from the data packet P. i Extract the user's electricity consumption characteristics, including daily average electricity consumption, peak electricity consumption and baseline electricity consumption;

[0037] Calculate the average value of each power usage feature in the cluster and combine them into a user's average power usage habit feature vector

[0038] The multivariate linear regression is combined with the user's average electricity consumption habit feature vector to predict the user's energy saving potential value. The expression is:

[0039]

[0040] Among them, R j represents the energy saving potential value of the jth cluster user, represents the average electricity consumption habit feature vector of users in the jth cluster, max(M) represents the maximum average electricity consumption in all clusters, represents the maximum eigenvalue of the data packet P in the jth cluster, k is the total number of clusters;

[0041] Based on the average energy-saving efficiency level of the user group, define an energy-saving potential threshold W;

[0042] When R j>W, the user is considered to have great energy-saving potential, and detailed and specific energy-saving suggestions are provided to the user, including replacing high-efficiency energy-saving equipment, optimizing electricity usage time and mode, and installing intelligent control systems;

[0043] When R j When ≤W, it is considered that the user has great energy-saving potential, and the user is encouraged to maintain the current energy-saving habits. At the same time, further improvement measures are provided, including selecting high-efficiency energy-saving equipment, reasonably arranging electricity use time and reducing ineffective power consumption.

[0044] As a preferred solution of the power marketing data management method of the present invention, wherein: the collecting of user feedback and optimizing the personalized energy-saving suggestion algorithm according to the user feedback, the specific steps are as follows:

[0045] Send energy-saving suggestions to users via text messages;

[0046] Set up online questionnaires, feedback forms and customer service hotlines to collect user feedback, including users' views on energy-saving suggestions, the effects after implementation and the problems encountered;

[0047] Adjust the value of energy saving potential threshold W according to user feedback;

[0048] If the feedback energy-saving effect is not good, the value of the energy-saving potential threshold W is increased;

[0049] If the energy-saving suggestions reported by users are too radical, the value of the energy-saving potential threshold W is reduced;

[0050] The adjusted energy-saving potential threshold W is used to adjust the targeted energy-saving suggestions recommended to the user.

[0051] In a second aspect, the present invention provides a power marketing data management system, including a data acquisition and preprocessing module, an anomaly detection and data screening module, a user power usage habit analysis module, a personalized energy-saving suggestion generation module, and a user feedback collection and algorithm optimization module;

[0052] The data collection and preprocessing module is used to collect users' electricity consumption data in real time and use edge computing devices to preprocess the collected data;

[0053] The anomaly detection and data screening module is used to perform real-time analysis on the pre-processed data on the edge computing device, identify abnormal power usage patterns, and filter out user power usage data marked as normal;

[0054] The user power usage habit analysis module is used to receive and store data from edge devices through the central server and analyze the user's power usage habits;

[0055] The personalized energy-saving suggestion generation module is used to develop a personalized energy-saving suggestion algorithm based on the user's electricity usage habits and recommend targeted energy-saving suggestions to users;

[0056] The user feedback collection and algorithm optimization module is used to collect user feedback and optimize the personalized energy-saving suggestion algorithm based on user feedback.

[0057] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the power marketing data management method as described in the first aspect of the present invention is implemented.

[0058] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the power marketing data management method as described in the first aspect of the present invention is implemented.

[0059] The beneficial effects of the present invention are as follows: by collecting and preprocessing users' electricity consumption data in real time and using edge computing devices for anomaly detection, the present invention achieves efficient data management and accurate identification of abnormal electricity consumption patterns. Normal electricity consumption data is sent to a central server for storage and analysis through a secure data transmission mechanism, thereby accurately identifying users' electricity consumption habits. On this basis, a personalized energy-saving suggestion algorithm is developed to provide users with targeted energy-saving suggestions, and the personalized energy-saving suggestion algorithm is continuously optimized through user feedback, ultimately improving the service quality and user experience of power marketing, promoting the realization of energy-saving and emission reduction goals, and improving data security and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0061] Figure 1 This is a flow chart of the power marketing data management method in Example 1.

[0062] Figure 2 This is a flow chart of the power marketing data management system in Example 1. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0066] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a power marketing data management method, comprising the following steps:

[0067] S1. Collect users’ electricity consumption data in real time and use edge computing devices to pre-process the collected data.

[0068] Furthermore, smart meters are installed at the metering points of power users to collect users' electricity consumption data in real time, including information such as the amount of electricity used, the time of electricity use, and the frequency of electricity use. At the same time, the collected user electricity consumption data is sent to the edge computing device;

[0069] Deploy edge computing devices near smart meters to clean, standardize and perform statistical analysis on the collected user electricity consumption data;

[0070] It should be noted that the missing value processing is specifically as follows: check whether there is missing electricity consumption data (such as electricity consumption, electricity consumption time, etc.), and the missing values ​​can be filled by interpolation method;

[0071] Outlier detection is specifically: using Z-score to identify abnormal power consumption records, such as a sudden surge or drop in power consumption, which may be caused by equipment failure or misoperation;

[0072] The specific standardization process is to use min-max scaling to convert values ​​in different ranges to the same range (such as between 0 and 1) to ensure that all data uses the same unit of measurement.

[0073] S2. On the edge computing device, analyze the preprocessed data, identify abnormal power usage patterns, and filter normal user power usage data based on the identification results.

[0074] Furthermore, an isolation forest model is constructed based on the preprocessed user electricity consumption data. The specific process is as follows: first, the cleaned and standardized user electricity consumption data is obtained from the edge computing device; then, this data is used to train the isolation forest algorithm, which constructs multiple isolation trees by randomly selecting attributes and data subsets to identify normal electricity consumption patterns; finally, abnormal electricity consumption behavior is identified through the anomaly score of the model. Records with higher scores are considered to be more abnormal, thereby helping to discover potential abnormal electricity consumption situations.

[0075] The number of trees in the isolation forest and the number of samples used for each tree are set according to actual needs. The actual needs refer to determining the configuration parameters of the model based on factors such as data set size, computing resource limitations, and anomaly detection accuracy requirements.

[0076] Using the average path length and sample size, the abnormal score of user electricity consumption data is calculated. The expression is:

[0077]

[0078] Where S(X,n) represents the anomaly score of data point X, n is the number of samples used in each tree, E[h(X)] is the average path length to a leaf node, h(X) is the number of edges required for a data point to reach a leaf node from the root node of the tree, X is the preprocessed user electricity consumption data, and c9n) represents the average path length of a complete binary tree with n nodes (the sum of the path lengths of all nodes plus 2, then divided by the total number of nodes n);

[0079] Based on the distribution of historical data, define an abnormal deviation threshold A to identify abnormal data points;

[0080] When S(X,n)>A, mark the current data point as abnormal power consumption data;

[0081] When S(X,n)≤A, mark the current data point as normal power consumption data;

[0082] The data points marked as normal are filtered out to form a user's normal electricity consumption data set.

[0083] It should also be noted that the anomaly score S(X,n) of each data point X is calculated using the isolation forest model, where n is the number of samples used in each tree, E[h(X)] is the average path length to the leaf node, and c(n) is the average path length of a complete binary tree with n nodes. By comparing the anomaly score S(X,n) with the pre-set anomaly deviation threshold A, it can be determined whether the data point is abnormal. When S(X,n)>A, the data point is marked as abnormal electricity consumption data; when S(X,n)≤A, the data point is marked as normal electricity consumption data. Finally, all electricity consumption data marked as normal are screened out to form a user's normal electricity consumption data set. This step provides a pure data source for subsequent data analysis, ensuring the accuracy and effectiveness of subsequent analysis (such as user electricity consumption habit analysis).

[0084] S3. Send the user's normal electricity usage data to the central server for storage. The central server analyzes the user's electricity usage habits based on the user's normal electricity usage data.

[0085] Furthermore, the filtered normal power consumption data is packaged to form a data packet P, which is expressed as:

[0086] P={X'1,X'2,…,X' m};

[0087] Where m is the total number of data points contained in the data packet;

[0088] The data packet P is encrypted using the AES-256 encryption algorithm, and the encrypted data packet is sent from the edge computing device to the central server via a secure TCP / IP protocol;

[0089] It should be noted that the process of encrypting data packet P using the AES-256 encryption algorithm includes: first preparing a 256-bit encryption key; then dividing the data packet P into multiple 128-bit data blocks according to the requirements of the AES algorithm; then using the key to encrypt each data block through a series of complex replacement and permutation operations, and finally obtaining an encrypted data packet.

[0090] The central server receives the data packet P from the edge computing device, decrypts the data in the received data packet P and verifies the data integrity, and stores the decrypted data in the database of the central server.

[0091] It should be noted that the specific process of decrypting the data in the received data packet P and verifying the data integrity is as follows: using the pre-shared 256-bit key to perform AES-256 decryption on the data packet P to restore the original data; then, verifying the integrity of the data by checking the integrity check code in the data packet or using a digital signature to ensure that the data has not been tampered with during transmission.

[0092] Using the K-means algorithm, calculate the cluster center c closest to the normal data point X' i , cluster the data point X' in the data packet P, the expression is:

[0093]

[0094] Among them, C(X') represents the index number of the cluster to which the normal data point X' belongs, X' is the normal data point that has been screened out, and the data point X' and the cluster center c are calculated. i The distance between

[0095] The average power consumption of the cluster to which the data point belongs is calculated by the cluster index number C(X') to which the data point belongs. The expression is:

[0096]

[0097] Among them, X' i represents the i-th data point marked as normal, Represents data point X' i Power consumption, C(X') j represents the set of all data points contained in the jth cluster, |C(X') j | represents the total number of data points in the jth cluster, M j represents the average power consumption of the jth cluster;

[0098] By calculating the average power consumption M of all clusters j Sort by size and select the median as the electricity consumption standard u;

[0099] When M j >u, it is considered that the current clustered user group has a high daily electricity consumption;

[0100] When M j When ≤u, it is considered that the daily electricity consumption of the current clustered user group is low.

[0101] It should also be noted that this process helps to identify the electricity consumption characteristics of different user groups and lays the foundation for providing targeted energy-saving suggestions in the future. Through these analyses, personalized energy-saving suggestions can be provided to users more accurately.

[0102] S4. Develop a personalized energy-saving suggestion algorithm based on the user's electricity usage habits and recommend targeted energy-saving suggestions to users.

[0103] Furthermore, by using statistical analysis methods, each data point X' is extracted from the data packet P. i Extract the user's electricity consumption characteristics, including daily average electricity consumption, peak electricity consumption and baseline electricity consumption;

[0104] Calculate the average value of each power usage feature in the cluster and combine them into a user's average power usage habit feature vector The expression is:

[0105]

[0106] in, represents the average daily electricity consumption of users in the jth cluster, represents the average peak power consumption of users in the jth cluster, represents the mean baseline electricity consumption of users in the jth cluster;

[0107] Among them, the average value of each power consumption feature in the cluster is calculated, and the expression is:

[0108]

[0109] Among them, g represents the total number of data points in the cluster, y is the index of the electricity usage feature, and μ yj represents the yth electricity consumption feature in the jth cluster, represents the average value of the yth electricity consumption feature in the jth cluster;

[0110] The multivariate linear regression is combined with the user's average electricity consumption habit feature vector to predict the user's energy saving potential value. The expression is:

[0111]

[0112] Among them, R j represents the energy saving potential value of the jth cluster user, represents the average electricity consumption habit feature vector of users in the jth cluster, max(M) represents the maximum average electricity consumption in all clusters, represents the maximum eigenvalue of the data packet P in the jth cluster, k is the total number of clusters;

[0113] Based on the average energy-saving efficiency level of the user group, define an energy-saving potential threshold W;

[0114] When R j When >W, it is considered that the energy-saving potential of users in the current cluster is large, and detailed and specific energy-saving suggestions are provided to users, including replacing high-efficiency energy-saving equipment, optimizing electricity usage time and mode, and installing intelligent control systems;

[0115] When R j When ≤W, it is considered that the energy-saving potential of users in the current cluster is large, and users are encouraged to maintain their current energy-saving habits. At the same time, further improvement measures are provided, including selecting high-efficiency energy-saving equipment, reasonably arranging power usage time, and reducing ineffective power consumption.

[0116] It should also be noted that the average energy-saving efficiency level of the user group is obtained by collecting the electricity consumption data of users before and after the implementation of energy-saving suggestions in historical data, calculating the energy-saving potential of each user group according to the energy-saving suggestion algorithm, comparing the electricity consumption data before and after the implementation of the energy-saving suggestions to evaluate the actual effect of the energy-saving suggestions, and calculating the energy-saving percentage or the saved electricity consumption, and finally summarizing the energy-saving effects of all users in the user group and calculating the average energy-saving efficiency level.

[0117] S5. Collect user feedback and optimize the personalized energy-saving suggestion algorithm based on the user feedback.

[0118] Furthermore, energy-saving suggestions can be sent to users via text messages;

[0119] Set up online questionnaires, feedback forms and customer service hotlines to collect user feedback, including users' views on energy-saving suggestions, the effects after implementation and the problems encountered;

[0120] Adjust the value of energy saving potential threshold W according to user feedback;

[0121] If the feedback energy-saving effect is not good, the value of the energy-saving potential threshold W is increased;

[0122] If the energy-saving suggestions reported by users are too radical, the value of the energy-saving potential threshold W is reduced;

[0123] Based on the adjusted energy-saving potential threshold W, new targeted energy-saving suggestions are recommended to the user.

[0124] It should also be noted that if the feedback on energy-saving effect is not good, the value of the energy-saving potential threshold W is increased to relax the standard of energy-saving suggestions and allow more users to achieve energy-saving goals; if the user feedback on energy-saving suggestions is too radical, the value of the energy-saving potential threshold W is lowered to reduce the strictness of the energy-saving suggestions and make the suggestions easier to implement. Based on the adjusted energy-saving potential threshold W, new targeted energy-saving suggestions are recommended to users again to ensure that the energy-saving suggestions are both practical and easy to implement, thereby improving user satisfaction and energy-saving effects.

[0125] This embodiment also provides a power marketing data management system, including: a data collection and preprocessing module, an anomaly detection and data screening module, a user power usage habit analysis module, a personalized energy-saving suggestion generation module, and a user feedback collection and algorithm optimization module;

[0126] The data collection and preprocessing module is used to collect users' electricity consumption data in real time and use edge computing devices to preprocess the collected data;

[0127] The anomaly detection and data screening module is used to perform real-time analysis on the pre-processed data on the edge computing device, identify abnormal power usage patterns, and filter out user power usage data marked as normal;

[0128] The user power usage habit analysis module is used to receive and store data from edge devices through the central server and analyze the user's power usage habits;

[0129] The personalized energy-saving suggestion generation module is used to develop a personalized energy-saving suggestion algorithm based on the user's electricity usage habits and recommend targeted energy-saving suggestions to users;

[0130] The user feedback collection and algorithm optimization module is used to collect user feedback and optimize the personalized energy-saving suggestion algorithm based on user feedback.

[0131] This embodiment also provides a computer device, which is suitable for the case of the power marketing data management method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the power marketing data management method proposed in the above embodiment.

[0132] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0133] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for implementing power marketing data management as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0134] In summary, the present invention achieves efficient data management and accurate identification of abnormal power usage patterns by: collecting and preprocessing users' power usage data in real time, and using edge computing devices for anomaly detection. Normal power usage data is sent to a central server for storage and analysis through a secure data transmission mechanism, thereby accurately identifying users' power usage habits. On this basis, a personalized energy-saving suggestion algorithm is developed to provide users with targeted energy-saving suggestions, and the personalized energy-saving suggestion algorithm is continuously optimized through user feedback, ultimately improving the service quality and user experience of power marketing, promoting the realization of energy-saving and emission reduction goals, and improving data security and user satisfaction.

[0135] Example 2, referring to Table 1, is the second example of the present invention. To further verify the advancement of the present invention, experimental simulation data of the power marketing data management method are provided.

[0136] 1,000 users from different regions were selected and their electricity consumption data in the past year were collected. The data set includes information such as the user's electricity consumption, electricity consumption time, and electricity consumption frequency. Smart meters are installed at each user's metering point, and edge computing devices are deployed near the smart meters to collect and pre-process electricity consumption data in real time.

[0137] First, the electricity consumption data of 1,000 users were collected in real time through smart meters, and the data was cleaned, standardized, and detected as outliers on edge computing devices to ensure data quality.

[0138] Secondly, the isolation forest model is used to identify abnormal electricity consumption patterns and filter out normal electricity consumption data to form a user's normal electricity consumption data set.

[0139] Next, the normal electricity consumption data is packaged and encrypted and transmitted to the central server for storage, and the user's electricity consumption habits are analyzed through the K-means algorithm to identify the electricity consumption characteristics of different user groups.

[0140] Finally, a personalized energy-saving recommendation algorithm was developed based on users' electricity usage habits, and the personalized energy-saving recommendation algorithm was continuously optimized through user feedback, which improved the service quality and user experience of power marketing.

[0141] The details are shown in Table 1

[0142] Table 1 Energy saving potential analysis table

[0143]

[0144] Through the data analysis of the above table, it can be clearly seen that the method of the present invention effectively processes and analyzes the user's electricity consumption data, identifies different user groups and their electricity consumption characteristics, and provides personalized energy-saving suggestions accordingly; for example, after 1.2% missing value processing and 2.5% outlier detection, the data standardization processing of user group 1 reached 98.7%, and the anomaly score threshold was set to 2.5. Its average electricity consumption was 350 kWh, and the energy-saving potential value was 0.6, which means that while maintaining daily electricity demand, user group 1 still has about 6% energy-saving space.

[0145] Through the power marketing data management method of the present invention, not only can the quality and reliability of the data be effectively improved, but also the electricity consumption characteristics of different user groups can be accurately identified, especially through the provision of personalized energy-saving suggestions, which reflects the significant effect of the present invention in improving the quality of power marketing services and user experience.

[0146] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for managing power marketing data, characterized in that: include, Collect users' electricity consumption data in real time and use edge computing devices to pre-process the collected data; On the edge computing device, the pre-processed data is analyzed to identify abnormal power usage patterns, and based on the identification results, normal user power usage data is screened; The user's normal electricity usage data is sent to the central server for storage. The central server analyzes the user's electricity usage habits based on the user's normal electricity usage data; Develop personalized energy-saving suggestion algorithms based on user electricity usage habits to recommend targeted energy-saving suggestions to users; Collect user feedback and optimize the personalized energy-saving suggestion algorithm based on user feedback.

2. The power marketing data management method according to claim 1, characterized in that: The real-time collection of user electricity consumption data and the use of edge computing devices to pre-process the collected data are as follows: Install smart meters at the metering points of electricity users to collect users' electricity consumption data in real time, including the amount of electricity used, the time of use, and the frequency of use. At the same time, the collected user electricity consumption data is sent to the edge computing device. Edge computing devices are deployed near smart meters to process missing values, standardize, and process outliers for the collected user electricity consumption data.

3. The power marketing data management method according to claim 2, characterized in that: The edge computing device performs real-time analysis on the pre-processed data to identify abnormal power consumption patterns, and based on the identification results, filters the user power consumption data marked as normal. The specific steps are as follows: An isolation forest model is constructed based on the preprocessed user electricity consumption data; Set the number of trees in the isolation forest and the number of samples used for each tree according to actual needs; Using the average path length and sample size, the abnormal score of user electricity consumption data is calculated. The expression is: Where S(X,n) represents the anomaly score of data point X, n is the number of samples used in each tree, E[h(X)] is the average path length to a leaf node, h(X) is the number of edges required for a data point to reach a leaf node from the root node of the tree, X is the preprocessed user electricity consumption data, and c(n) represents the average path length of a complete binary tree with n nodes; Based on the distribution of historical data, define an abnormal deviation threshold A to identify abnormal data points; When S(X,n)>A, mark the current data point as abnormal power consumption data; When S(X,n)≤A, mark the current data point as normal power consumption data; The data points marked as normal are filtered out to form a user's normal electricity consumption data set.

4. The power marketing data management method according to claim 3, characterized in that: The specific steps of sending the user's normal electricity consumption data to the central server for storage are as follows: Pack the filtered normal power consumption data into a data packet P; The data packet P is encrypted using the AES-256 encryption algorithm, and the encrypted data packet is sent from the edge computing device to the central server via a secure TCP / IP protocol; The central server receives the data packet P from the edge computing device, decrypts the data in the received data packet P and verifies the data integrity, and stores the decrypted data in the database of the central server.

5. The power marketing data management method according to claim 4, characterized in that: The central server analyzes the user's electricity usage habits based on the user's normal electricity usage data. The specific steps are as follows: Using the K-means algorithm, calculate the cluster center c closest to the normal data point X' i , cluster the data points in the data packet P, the expression is: Among them, C(X') represents the index number of the cluster to which the normal data point X' belongs, X' is the normal data point that has been screened out, and the data point X' and the cluster center c are calculated. i The distance between The average power consumption of the cluster to which the data point belongs is calculated by the cluster index number C(X') to which the data point belongs. The expression is: Among them, X' i represents the i-th data point marked as normal, Represents data point X' i Power consumption, C(X') j represents the set of all data points contained in the jth cluster, |C(X') j | represents the total number of data points in the jth cluster, M j represents the average power consumption of the jth cluster; By calculating the average power consumption M of all clusters j Sort by size and select the median as the electricity consumption standard u; When M j >u, it means that the current clustered user group has a high daily electricity consumption; When M j When ≤u, it means that the daily electricity consumption of the current clustered user group is low.

6. The power marketing data management method according to claim 5, characterized in that: According to the user's electricity usage habits, a personalized energy-saving suggestion algorithm is developed to recommend targeted energy-saving suggestions to users. The specific steps are as follows: By statistical analysis, each data point X' is extracted from the data packet P. i Extract the user's electricity consumption characteristics, including daily average electricity consumption, peak electricity consumption and baseline electricity consumption; Calculate the average value of each power usage feature in the cluster and combine them into a user's average power usage habit feature vector The multivariate linear regression is combined with the user's average electricity consumption habit feature vector to predict the user's energy saving potential value. The expression is: Among them, R j represents the energy saving potential value of the jth cluster user, represents the average electricity consumption habit feature vector of users in the jth cluster, max(M) represents the maximum average electricity consumption in all clusters, represents the maximum eigenvalue of the packet P in the jth cluster, k is the total number of clusters; Based on the average energy-saving efficiency level of the user group, define an energy-saving potential threshold W; When R j When the power consumption is greater than W, the user is considered to have great energy-saving potential, and detailed and specific energy-saving suggestions are provided to the user, including replacement of high-efficiency energy-saving equipment, optimization of electricity usage time and mode, and installation of intelligent control systems; When R j When ≤W, it is considered that the user has great energy-saving potential, and the user is encouraged to maintain the current energy-saving habits. At the same time, further improvement measures are provided, including selecting high-efficiency energy-saving equipment, reasonably arranging electricity use time and reducing ineffective power consumption.

7. The power marketing data management method according to claim 6, characterized in that: The specific steps of collecting user feedback and optimizing the personalized energy-saving suggestion algorithm according to the user feedback are as follows: Send energy-saving suggestions to users via text messages; Set up online questionnaires, feedback forms and customer service hotlines to collect user feedback, including users' views on energy-saving suggestions, the effects after implementation and the problems encountered; Adjust the value of energy saving potential threshold W according to user feedback; If the feedback energy-saving effect is not good, the value of the energy-saving potential threshold W is increased; If the energy-saving suggestions reported by users are too radical, the value of the energy-saving potential threshold W is reduced; The adjusted energy-saving potential threshold W is used to adjust the targeted energy-saving suggestions recommended to the user.

8. A power marketing data management system, based on the power marketing data management method according to any one of claims 1 to 7, characterized in that: It includes data collection and preprocessing module, anomaly detection and data screening module, user electricity usage habit analysis module, personalized energy-saving suggestion generation module and user feedback collection and algorithm optimization module; The data collection and preprocessing module is used to collect users' electricity consumption data in real time and use edge computing devices to preprocess the collected data; The anomaly detection and data screening module is used to perform real-time analysis on the pre-processed data on the edge computing device, identify abnormal power usage patterns, and filter out user power usage data marked as normal; The user power usage habit analysis module is used to receive and store data from edge devices through the central server and analyze the user's power usage habits; The personalized energy-saving suggestion generation module is used to develop a personalized energy-saving suggestion algorithm based on the user's electricity usage habits and recommend targeted energy-saving suggestions to users; The user feedback collection and algorithm optimization module is used to collect user feedback and optimize the personalized energy-saving suggestion algorithm based on user feedback.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the power marketing data management method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power marketing data management method according to any one of claims 1 to 7 are implemented.

Images